Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly and openWorld, so the description carries the rest and does so well: 15 MB size cap, page-by-page output shape, the scanned/no-text-layer failure mode, 1-hour caching, and pricing with accepted payment rails. It stops short of saying what happens when max_pages/max_chars truncate the result or what a failed download/payment looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Five short sentences, front-loaded with the action, then output shape, failure mode, caching, and price. Nothing is redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description adequately sketches the return payload (text per page plus title, author, page count) and covers cost and latency expectations. It falls short only on the truncation parameters and on error behavior, which matter for a paid, rate-limited external fetch.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50%: url and tx are documented in the schema, but max_chars and max_pages have no description anywhere, and with their large defaults (50,000 chars / 50 pages) they materially affect whether the caller gets full text. The description's "page by page" hints at page handling but adds no meaning for either limit, so it does not compensate for the gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource+input form: "Extract text from a PDF by URL." This distinguishes it from the sibling fetch (raw retrieval) and youtube_transcript (different source type), and the follow-up sentence specifies exactly what is returned.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the resource type, and the scanned-PDF caveat signals when the tool will underperform. However, it never explicitly contrasts with the sibling fetch tool (why not just fetch the PDF?) nor states prerequisites such as the URL needing to be public.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.